from safetensors.torch import load_file
from huggingface_hub import hf_hub_download
device = torch.device("cuda")

model = AutoModelForCausalLM.from_pretrained(f"{REPO_NAME}-tinyllama-qlora", device_map="auto")
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(f"{REPO_NAME}-tinyllama-qlora")
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"